© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3134
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and displacement

    oai_token-act-pair · gpt-3.5-turbo

    quantities and statistics relating to civilian casualties and displacement in conflict scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patent
    -0.91
     Advertising
    -0.80
     Teach
    -0.79
    é¾įå¥ij士
    -0.78
    wcsstore
    -0.77
     FCC
    -0.76
    omial
    -0.75
     Consumer
    -0.74
     Competitive
    -0.74
     Boolean
    -0.74
    POSITIVE LOGITS
     perished
    1.62
     evacuated
    1.40
     fleeing
    1.31
     casualties
    1.30
     wounded
    1.28
     injured
    1.27
     killed
    1.26
     massac
    1.26
     survivors
    1.23
     displaced
    1.22
    Activations Density 0.587%

    No Known Activations